def test_CanonicalInstanceSplitter(
start,
target,
is_train: bool,
use_prediction_features: bool,
allow_target_padding: bool,
):
train_length = 100
pred_length = 13
t = transform.CanonicalInstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
instance_sampler=(transform.UniformSplitSampler(
p=1.0,
min_past=train_length,
) if is_train else (
transform.ValidationSplitSampler()
if allow_target_padding else transform.TestSplitSampler())),
instance_length=train_length,
prediction_length=pred_length,
time_series_fields=["some_time_feature"],
allow_target_padding=allow_target_padding,
use_prediction_features=use_prediction_features,
)
assert_serializable(t)
other_feat = np.arange(len(target) + 100)
data = {
"start": start,
"target": target,
"some_time_feature": other_feat,
"some_other_col": "ABC",
}
out = list(t.flatmap_transform(data, is_train=is_train))
min_num_instances = 1 if allow_target_padding and not is_train else 0
if is_train:
assert len(out) == max(min_num_instances,
len(target) - train_length + 1)
else:
assert len(out) == 1
for o in out:
assert "target" not in o
assert "future_target" not in o
assert "some_time_feature" not in o
assert "some_other_col" in o
assert len(o["past_some_time_feature"]) == train_length
assert len(o["past_target"]) == train_length
if use_prediction_features and not is_train:
assert len(o["future_some_time_feature"]) == pred_length
def test_multi_dim_transformation(is_train):
train_length = 10
first_dim: list = list(np.arange(1, 11, 1))
first_dim[-1] = "NaN"
second_dim: list = list(np.arange(11, 21, 1))
second_dim[0] = "NaN"
ds = gluonts.dataset.common.ListDataset(
data_iter=[{"start": "2012-01-01", "target": [first_dim, second_dim]}],
freq="1D",
one_dim_target=False,
)
pred_length = 2
# Looks weird - but this is necessary to assert the nan entries correctly.
first_dim[-1] = np.nan
second_dim[0] = np.nan
t = transform.Chain(
trans=[
transform.AddTimeFeatures(
start_field=FieldName.START,
target_field=FieldName.TARGET,
output_field="time_feat",
time_features=[
time_feature.DayOfWeek(),
time_feature.DayOfMonth(),
time_feature.MonthOfYear(),
],
pred_length=pred_length,
),
transform.AddAgeFeature(
target_field=FieldName.TARGET,
output_field="age",
pred_length=pred_length,
log_scale=True,
),
transform.AddObservedValuesIndicator(
target_field=FieldName.TARGET,
output_field="observed_values",
imputation_method=None,
),
transform.VstackFeatures(
output_field="dynamic_feat",
input_fields=["age", "time_feat"],
drop_inputs=True,
),
transform.InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
instance_sampler=(
transform.ExpectedNumInstanceSampler(
num_instances=4, min_future=pred_length
)
if is_train
else transform.TestSplitSampler()
),
past_length=train_length,
future_length=pred_length,
time_series_fields=["dynamic_feat", "observed_values"],
output_NTC=False,
),
]
)
assert_serializable(t)
if is_train:
for u in t(iter(ds), is_train=True):
assert_shape(u["past_target"], (2, 10))
assert_shape(u["past_dynamic_feat"], (4, 10))
assert_shape(u["past_observed_values"], (2, 10))
assert_shape(u["future_target"], (2, 2))
assert_padded_array(
u["past_observed_values"],
np.array([[1.0] * 9 + [0.0], [0.0] + [1.0] * 9]),
u["past_is_pad"],
)
assert_padded_array(
u["past_target"],
np.array([first_dim, second_dim]),
u["past_is_pad"],
)
else:
for u in t(iter(ds), is_train=False):
assert_shape(u["past_target"], (2, 10))
assert_shape(u["past_dynamic_feat"], (4, 10))
assert_shape(u["past_observed_values"], (2, 10))
assert_shape(u["future_target"], (2, 0))
assert_padded_array(
u["past_observed_values"],
np.array([[1.0] * 9 + [0.0], [0.0] + [1.0] * 9]),
u["past_is_pad"],
)
assert_padded_array(
u["past_target"],
np.array([first_dim, second_dim]),
u["past_is_pad"],
)
def test_InstanceSplitter(
start, target, lead_time: int, is_train: bool, pick_incomplete: bool
):
train_length = 100
pred_length = 13
t = transform.InstanceSplitter(
target_field=FieldName.TARGET,
is_pad_field=FieldName.IS_PAD,
start_field=FieldName.START,
forecast_start_field=FieldName.FORECAST_START,
instance_sampler=(
transform.UniformSplitSampler(
p=1.0,
min_past=0 if pick_incomplete else train_length,
min_future=lead_time + pred_length,
)
if is_train
else transform.TestSplitSampler(
min_past=0 if pick_incomplete else train_length
)
),
past_length=train_length,
future_length=pred_length,
lead_time=lead_time,
time_series_fields=["some_time_feature"],
)
assert_serializable(t)
other_feat = np.arange(len(target) + 100)
data = {
"start": start,
"target": target,
"some_time_feature": other_feat,
"some_other_col": "ABC",
}
if not is_train and not pick_incomplete and len(target) < train_length:
with pytest.raises(AssertionError):
out = list(t.flatmap_transform(data, is_train=is_train))
return
else:
out = list(t.flatmap_transform(data, is_train=is_train))
if is_train:
assert len(out) == max(
0,
len(target)
- pred_length
- lead_time
+ 1
- (0 if pick_incomplete else train_length),
)
else:
assert len(out) == 1
for o in out:
assert "target" not in o
assert "some_time_feature" not in o
assert "some_other_col" in o
assert len(o["past_some_time_feature"]) == train_length
assert len(o["past_target"]) == train_length
if is_train:
assert len(o["future_target"]) == pred_length
assert len(o["future_some_time_feature"]) == pred_length
else:
assert len(o["future_target"]) == 0
assert len(o["future_some_time_feature"]) == pred_length